Surrogate Modeling of Musculoskeletal Systems Using Artificial Neural Networks
Organization:
Funded by: | - Health Holland and Stryker |
PhD: |  |
Supervisors: | chair MIA:  Daily supervisor:  |
Collaboration: |
Company: |
Description:
Osteoarthritis (OA) is the most common degenerative joint disease, affecting millions of people worldwide. The knee is one of the most commonly affected joints. Total knee arthroplasty (TKA) is an effective surgical treatment for end-stage knee OA. However, dissatisfaction for one in five patients persists. TKA aims to improve patients’ knee functioning and reduce pain. One of the main factors influencing post-operative knee function and patient satisfaction is the position of the implant components within the knee joint. Traditional surgical approaches aim for a straight-leg alignment in TKA; however, this may not reflect the natural anatomy of the patient. Novel alignment strategies have been proposed, but none consider reconstructing the knee as before the disease's onset. In previous studies, a musculoskeletal model-based approach has been developed to predict optimal implant positioning to restore pre-diseased knee functioning and improve patient satisfaction. However, its computational complexity limits implementation in clinical practice. The objective of this research project is to overcome this by replacing the slow musculoskeletal model with a fast AI-driven model.
This project is part of PROPEL (Personalized Robotic surgery Optimization through Precision and Enhanced ModeLing), a collaboration between the University of Twente, Radboudumc, and Stryker.
Output:
2025
2024
2023
Pictures:
